Re: [PATCH V2 1/3] ntb: Add a module option to control affinity of DMA channels

[Dave Jiang <dave.jiang@intel.com>]

On 05/04/2017 01:21 PM, Gary R Hook wrote:
> The DMA channel(s)/memory used to transfer data to an NTB device
> may not be required to be on the same node as the device. Add a
> module parameter that allows any candidate channel (aside from
> node assocation) and allocated memory to be used.
> 
> Signed-off-by: Gary R Hook <gary.hook@amd.com>
> ---
>  drivers/ntb/test/ntb_perf.c |   16 ++++++++++++++--
>  1 file changed, 14 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c
> index 42756a98a728..bfceae0e6477 100644
> --- a/drivers/ntb/test/ntb_perf.c
> +++ b/drivers/ntb/test/ntb_perf.c
> @@ -101,6 +101,10 @@
>  module_param(use_dma, bool, 0644);
>  MODULE_PARM_DESC(use_dma, "Using DMA engine to measure performance");
>  
> +static bool on_node = true; /* default to 1 */
> +module_param(on_node, bool, 0644);
> +MODULE_PARM_DESC(on_node, "Run threads only on NTB device node (default: true)");
> +
>  struct perf_mw {
>  	phys_addr_t	phys_addr;
>  	resource_size_t	phys_size;
> @@ -345,6 +349,10 @@ static int perf_move_data(struct pthr_ctx *pctx, char __iomem *dst, char *src,
>  
>  static bool perf_dma_filter_fn(struct dma_chan *chan, void *node)
>  {
> +	/* Is the channel required to be on the same node as the device? */
> +	if (!on_node)
> +		return true;
> +
>  	return dev_to_node(&chan->dev->device) == (int)(unsigned long)node;
>  }
>  
> @@ -682,7 +690,8 @@ static ssize_t debugfs_run_write(struct file *filp, const char __user *ubuf,
>  		pr_info("Fix run_order to %u\n", run_order);
>  	}
>  
> -	node = dev_to_node(&perf->ntb->pdev->dev);
> +	node = on_node ? dev_to_node(&perf->ntb->pdev->dev)
> +		       : NUMA_NO_NODE;
>  	atomic_set(&perf->tdone, 0);
>  
>  	/* launch kernel thread */
> @@ -781,7 +790,10 @@ static int perf_probe(struct ntb_client *client, struct ntb_dev *ntb)
>  
>  	node = dev_to_node(&pdev->dev);
>  
> -	perf = kzalloc_node(sizeof(*perf), GFP_KERNEL, node);
> +	if (on_node)
> +		perf = kzalloc_node(sizeof(*perf), GFP_KERNEL, node);
> +	else
> +		perf = kzalloc(sizeof(*perf), GFP_KERNEL);

Is this necessary when NUMA_NO_NODE is passed in?

>  	if (!perf) {
>  		rc = -ENOMEM;
>  		goto err_perf;
>